A tight, highly actionable reference: concrete formats, runnable make commands, and a validation checklist, with no padding or beginner-level explanation. Its only real flaws are a duplicated type list (conciseness) and the absence of explicit failure/recovery guidance after a failed checklist step.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no explanation of what a PR or conventional commit is. The one clear redundancy is the Type list appearing twice (a full table under 'PR Title Format' and again as a bullet list under 'Commit Message Format' despite saying 'Same convention as PR titles'), which is exactly the 'minor instances that could be trimmed' of the 4 anchor; the 5 anchor requires every token to earn its place.	4 / 5
Actionability	Guidance is fully concrete and executable: an exact title template, a type table with unambiguous 'when to use' criteria, eleven copy-paste example titles/commits, runnable checklist commands ('make test-backend-app', 'make typecheck-web', 'make generate-api', 'make staging') with a specific committed artifact path, and a five-part PR body structure. This matches the 5 anchor — instruction-only guidance that is specific and covers the common cases.	5 / 5
Workflow Clarity	The Workflow section gives a clear 4-step sequence (identify scope → format titles/commits → run checklist → open PR) and the Pre-PR Checklist provides explicit validation checkpoints tied to commands. It falls short of the 5 anchor because there is no error-recovery guidance (what to do when 'make staging' or typecheck fails) — the feedback loop is implied by the checklist but not stated.	4 / 5
Progressive Disclosure	This is a single-file skill with no bundle directories, and nothing in the ~90-line body warrants splitting into separate files — all content is overview-level and appropriately placed inline. Sections are clearly headed and easy to navigate, matching the simple-skill case in the rubric's scoring notes where well-organized sections alone earn a 5.	5 / 5
	Total	18 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-formed description: concrete, third-person-styled, with an explicit 'Use when' trigger clause and domain scoping ('for SkillHub'). Its main gap is trigger coverage — only one 'when' phrasing where richer synonym coverage (PRs, merge requests, submit changes) would push it to the top anchor.

Dimension	Reasoning	Score
Specificity	The description lists several specific capabilities — 'PR title format, commit conventions, and pre-PR checklist' — anchored to a concrete domain (SkillHub). It falls just short of the 5 anchor because the items are topic nouns rather than a comprehensive list of concrete actions (e.g., 'format PR titles', 'write commit messages', 'run pre-PR checks').	4 / 5
Completeness	It answers both parts: the 'what' ('PR title format, commit conventions, and pre-PR checklist for SkillHub') and an explicit 'when' clause ('Use when preparing or reviewing pull requests'). The 'when' could be more specific with additional trigger phrases (e.g., 'when the user mentions PRs, commits, or asks to submit changes'), so it matches the 4 anchor rather than 5; it clearly exceeds the 3 anchor where 'when' is missing or weakly implied.	4 / 5
Trigger Term Quality	Natural trigger phrases are present: 'Use when preparing or reviewing pull requests', plus keywords like 'PR title', 'commit conventions', 'pre-PR checklist'. Coverage is good but misses common variations a user might say, such as 'PRs', 'merge request', or 'opening a PR', which the 5 anchor requires.	4 / 5
Distinctiveness Conflict Risk	The 'for SkillHub' scoping and the PR-submission focus give it a clear niche with minimal conflict risk. Minor overlap remains with generic git commit-message skills, keeping it below the 5 anchor, but it is far more distinct than the broad 3-anchor example.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: iflytek/skillhub
Path: .agents/skills/pr-submission/SKILL.md
Commit: 7352597

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.